On reduced order identification; revisiting 'On some system identification techniques for adaptive filtering'

T. Soderstrom and P. Stoica (1988) have previously discussed three algorithms: the Steiglitz-McBride method (SMM), the recursive gradient method (RGM), and the instrumental variable method (IVM). These adaptive algorithms are revisited. Their stability and convergence points are studied and discussed under a reduced-order framework which is more realistic in a practical situation. It is concluded that no algorithm has compelling advantages over the others; each one has its own advantages and disadvantages. One is faced with a tradeoff in choosing one against the others in a specific application.>